Selected practice
Volcengine Ark support agent
Moving beyond fragmented chunk matching: teaching an agent to navigate authoritative documentation like a human reader.
Iteration strategy for Doubao Coding models
When static benchmarks plateau, how do you turn anonymous real-task testing and failure traces into model improvements?
Enterprise AI design and delivery
Turning "what the model can do" into explainable, mutually accepted engineering outcomes.
Dynamic tool retrieval for vehicle control
Faced with over 400 vehicle APIs, how do you retrieve and call the right tool within five seconds?
Independent explorations
Turning recurring questions outside of work into runnable, testable experiments.
01Building a measure for “AI-sounding” writing
Start with whether people want to keep reading, then look for linguistic signals that explain why.
ACRON
An open-source agent exploring context signal-to-noise ratio in long-running collaboration.
Let’s talk
If you’re building AI products, designing evaluations, or figuring out how agents hold up in the wild, I’d love to exchange notes.